AI for Developers

AI for Developers

Duration: 2 Days

Description

This course introduces working developers to building software that uses generative AI. Rather than training models, participants learn to integrate existing large language models into applications: how the models work at a practical level, how to call them through APIs, how to design prompts in code, and how to handle responses, errors, and cost. Coverage includes structured output and basic tool-calling, the building blocks behind today’s AI coding assistants and agents. Through hands-on exercises, developers build their first AI-powered features and gain the foundation needed for more advanced application and agent development.
Class time is divided between instructor-led explanation (40 percent) and hands-on coding (60 percent).

Audience

Software developers and engineers who can program (Python recommended) and want to start building applications that use generative AI, including those who already use AI coding assistants and want to build with the underlying APIs. Suitable for those new to AI development but comfortable writing code.

Objectives

  • Explain how large language models work from a developer’s perspective
  • Call AI models through APIs and handle responses in code
  • Design and manage prompts programmatically
  • Handle errors, rate limits, streaming, and cost considerations
  • Build a simple AI-powered application feature
  • Recognize patterns and pitfalls in AI application development

Prerequisites

Participants should be comfortable writing code. The following will help:

  • Working knowledge of Python or a similar language (see Python Foundations)
  • Familiarity with generative AI concepts
  • Comfort using APIs and reading documentation

Related AI Courses

See the full AI training roadmap and course directory for how this fits into a broader learning path.

After this course, continue with Building LLM Applications and Introduction to AI Agents, or explore Prompt Engineering to sharpen your prompt design skills.

Course Outline

  • Module 1 – Course Introduction
    • Welcome and objectives
    • How LLMs work for developers
    • The AI application landscape
  • Module 2 – Calling AI Models
    • Working with model APIs
    • Authentication and configuration
    • Requests, responses, and tokens
    • Hands-on exercise: your first API call
  • Module 3 – Prompts in Code
    • Constructing prompts programmatically
    • Templating and dynamic input
    • System, user, and assistant roles
    • Managing prompt versions
  • Module 4 – Handling Responses
    • Parsing and validating output
    • Structured output and JSON
    • Streaming responses
    • Error handling, retries, and rate limits
  • Module 5 – Practical Concerns
    • Token usage and cost management
    • Latency and performance
    • Logging, testing, and debugging AI features
    • Safety and content considerations
  • Module 6 – Building an AI Feature
    • Designing a simple AI-powered feature
    • Putting the pieces together
    • Hands-on exercise: build and test an AI feature
  • Module 7 – Course Wrap-Up
    • Key takeaways
    • Resources for continued learning
    • Next steps toward LLM apps and agents